Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1063798 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1264901 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7043. Min Act: -0.0000

Data Index: 588125 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5833. Min Act: -0.0000

Data Index: 847121 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5318. Min Act: -0.0000

Data Index: 721273 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1594012 (Python Code)

Max Activating Token Index: 283

Text #6

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5136. Min Act: -0.0000

Data Index: 251947 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1654889 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.4655. Min Act: -0.0000

Data Index: 440003 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1246715 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.4235. Min Act: -0.0000

Data Index: 664789 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.4239. Min Act: -0.0000

Data Index: 110825 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.3884. Min Act: -0.0000

Data Index: 123286 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1372534 (Python Code)

Max Activating Token Index: 733

Text #14

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1393740 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1288749 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.3995. Min Act: -0.0000

Data Index: 866085 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.3695. Min Act: -0.0000

Data Index: 410269 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1145082 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.3957. Min Act: -0.0000

Data Index: 82491 (C4 (Web Text))

Max Activating Token Index: 56